Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
A skill your agent uses when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs…
Install Dataset Benchmark Discovery
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discovery --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .claude/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .claude/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discoveryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .agents/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .agents/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .cursor/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .cursor/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Citrus-bit/Anaxa.git --path skills/public/dataset-benchmark-discovery--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .gemini/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .gemini/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discoveryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .github/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .github/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Citrus-bit/Anaxa dataset-benchmark-discovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/public/dataset-benchmark-discovery .opencode/skills/dataset-benchmark-discovery && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "dataset-benchmark-discovery" agent skill from https://github.com/Citrus-bit/Anaxa/tree/main/skills/public/dataset-benchmark-discovery into .opencode/skills/dataset-benchmark-discovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dataset-benchmark-discovery", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
dataset-benchmark-discovery- GitHub stars
- 120
- Token cost
- ~479 tokens
- SKILL.md length
- 190 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs…
- Works in 4 steps: Call… → Review candidates by task fit,… → If the user wants experiments, choose… → …
- The user asks for latest datasets
- SKILL.md covers Core Rules, Workflow and Output Discipline
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Dataset Benchmark Discovery is an agent skill from Citrus-bit/Anaxa. Use when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs complete experimental validation. This skill routes to the datasetbenchmarkdiscovery tool and keeps access/license limits explicit.
Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. The repository describes itself as: Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。 The licence is MIT.
When your agent uses it
- The user asks for latest datasets
- Benchmark suites
- SOTA comparisons
- Dataset selection for experiments
Example prompts
- “/dataset-benchmark-discovery”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Call dataset_benchmark_discovery(topic=..., scope=...).
- Review candidates by task fit, recency/version, license/access, metric alignment, and reproducibility risk.
- If the user wants experiments, choose feasible datasets and pass local paths or uploaded files into experiment_lab.
- If writing a paper before experiments are complete, describe benchmark choices as planned validation, not completed results.
What it can do on your machine
Read from SKILL.md and the folder at commit d57c708. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dataset Benchmark Discovery loads about 479 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 190 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Citrus-bit/Anaxa at commit d57c708, republished under its MIT licence (© Citrus-bit). 190 words, ~479 tokens.
Download SKILL.mdSave it as
.claude/skills/dataset-benchmark-discovery/SKILL.md (or your agent's skills folder).- name
- dataset-benchmark-discovery
- description
- Use when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs complete experimental validation. This skill routes to the dataset_benchmark_discovery tool and keeps access/license limits explicit.
Dataset Benchmark Discovery
Use this skill before experiment planning or manuscript drafting when the user needs datasets, benchmarks, metrics, baselines, or leaderboard context.
Core Rules
- Prefer the
dataset_benchmark_discoverytool over generic browsing for dataset and benchmark mapping. - Do not download restricted, login-gated, license-gated, or private data unless the user has provided access and the environment is configured for it.
- Treat
dataset_benchmark_map.jsonas a candidate map. It can support dataset selection and experiment planning, but it is not executed experimental evidence. - Verify version/date, license, standard split, metric definition, and official leaderboard status before writing strong manuscript claims.
- Route actual evaluation to
experiment_lab, then useclaim_support_matrix.jsonfor manuscript claim support.
Workflow
- Call
dataset_benchmark_discovery(topic=..., scope=...). - Review candidates by task fit, recency/version, license/access, metric alignment, and reproducibility risk.
- If the user wants experiments, choose feasible datasets and pass local paths or uploaded files into
experiment_lab. - If writing a paper before experiments are complete, describe benchmark choices as planned validation, not completed results.
Output Discipline
When summarizing results, report:
- strongest candidate datasets/benchmarks
- access and license risks
- standard metrics and splits when detected
- baseline/SOTA hints when available
- what still needs manual verification
© Citrus-bit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/public/dataset-benchmark-discovery of Citrus-bit/Anaxa.
Open the folder on GitHubat commit d57c708
Compare with similar skills
Dataset Benchmark Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Dataset Benchmark Discovery this skillCitrus-bit/Anaxa | 120 | — | ~479 | Automated safety check: Pass | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| 1passwordtrpc-group/trpc-agent-go | 1.9k | 14 repos | ~656 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
1password
trpc-group/trpc-agent-go
Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.
Planning With Files
jarrodwatts/claude-code-config
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.
More from Citrus-bit/Anaxa
All 15 skills in this repoNature Figure
Citrus-bit/Anaxa
Submission-grade Nature/high-impact journal figure workflow for Python or R.
Chart Visualization
Citrus-bit/Anaxa
A skill your agent uses whenever the user wants a chart, graph, plot, dashboard visual, or asks to visualize structured numbers, trends, comparisons, proportions, distributions, correlations…
Claude To Medrixflow
Citrus-bit/Anaxa
Interact with MedrixFlow AI agent platform via its HTTP API.
Fireworks Tech Graph
Citrus-bit/Anaxa
A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.
Bootstrap
Citrus-bit/Anaxa
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation.
Deep Research
Citrus-bit/Anaxa
A skill your agent uses for general web research that needs current online information, multiple source angles, and synthesis, when no more specific research skill applies.
Related
Categories
Questions about Dataset Benchmark Discovery
What does Dataset Benchmark Discovery do?
A skill your agent uses when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs…. Dataset Benchmark Discovery is an agent skill from Citrus-bit/Anaxa. Use when the user asks for latest datasets, benchmark suites, leaderboards, baseline or SOTA comparisons, dataset selection for experiments, or evidence that a paper needs complete experimental validation.
When should I use Dataset Benchmark Discovery?
Dataset Benchmark Discovery fits situations like: the user asks for latest datasets; benchmark suites; SOTA comparisons; dataset selection for experiments.
How do I install Dataset Benchmark Discovery in Claude Code?
Run `npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a claude-code`. Or copy the skill folder (skills/public/dataset-benchmark-discovery in Citrus-bit/Anaxa) into .claude/skills/dataset-benchmark-discovery in your project. Claude Code loads it when a task matches its description.
How do I install Dataset Benchmark Discovery in Codex?
Run `npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a codex`. Or copy the skill folder (skills/public/dataset-benchmark-discovery in Citrus-bit/Anaxa) into .agents/skills/dataset-benchmark-discovery in your project. Codex loads it when a task matches its description.
Can I use Dataset Benchmark Discovery in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Citrus-bit/Anaxa --skill dataset-benchmark-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dataset-benchmark-discovery, .gemini/skills/dataset-benchmark-discovery, .github/skills/dataset-benchmark-discovery and .opencode/skills/dataset-benchmark-discovery in your project.
What does Dataset Benchmark Discovery need to run?
SKILL.md names no scripts, command-line tools or credentials: Dataset Benchmark Discovery is instructions for the agent only.
Does Dataset Benchmark Discovery access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Dataset Benchmark Discovery safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Dataset Benchmark Discovery use?
Dataset Benchmark Discovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dataset Benchmark Discovery use?
About 479 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Dataset Benchmark Discovery?
Skills that share tags, products or a category with Dataset Benchmark Discovery: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dataset Benchmark Discovery?
Citrus-bit (a GitHub user) maintains it in Citrus-bit/Anaxa, which has 120 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 7, 2026.
Source: Citrus-bit/Anaxa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.